Image Generation

Ctrl-u: Robust conditional image generation via uncertainty-aware reward modeling
guiyu-zhang

Guiyu Zhang, Huan-ang Gao, Zijian Jiang, Hao Zhao, Zhedong Zheng
International Conference on Learning Representations (ICLR), 2025 PDF Code 中文解读

Instilling Multi-round Thinking to Text-guided Image Generation
Lidong Zeng, Zhedong Zheng, Yinwei Wei, tat-seng-chua

Tat-seng Chua
arXiv:2401.08472, 2024